Digitizing Hand-Marked Inspection Sheets via Arrow-Text Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manual inspection sheets in heavy industries are cumbersome to maintain and difficult to digitize due to unstructured data formats, making data extraction and digitization inefficient.

Innovation Solution

A processor-implemented document digitization system that performs component localization, arrow head-tail localization, text detection, and mapping to associate text with machine zones in inspection sheets, using techniques like template matching and deep neural networks for accurate data extraction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual inspection sheets are used for recording inspection data, then flexibility in marking and commenting is improved, but data extraction efficiency and digitization capability deteriorate

Engineering Contradiction:
Improveflexibility in marking and commentingVSAvoiddata extraction efficiency
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The patent creates a digital copy of the manual inspection sheet by detecting arrows, text, and line diagrams, then mapping their spatial relationships to reconstruct the inspection data in structured digital format. This copying approach preserves the flexibility of manual marking while enabling efficient digital extraction and processing

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces manual data extraction processes with automated image processing and machine learning algorithms. The system automatically detects visual elements, determines their spatial relationships, and extracts structured data without requiring manual intervention, thereby substituting mechanical manual work with automated computational processes

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If data is manually penned down on inspection sheets, then ease of recording is improved, but data digitization capability deteriorates

Engineering Contradiction:
Improveease of recordingVSAvoiddata digitization capability
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The system creates a digital replica of the manually filled inspection sheet by detecting and digitizing all visual elements including handwritten text, drawn arrows, and line diagrams. This copying process transforms analog manual records into structured digital data while preserving the original information content

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent introduces an intermediary processing layer that bridges manual recording and digital storage. The system uses image processing algorithms and spatial relationship analysis as intermediaries to convert manually penned data into machine-readable formats, preventing information loss during the transition from analog to digital

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If multiple inspection sheets are maintained for multiple machines, then inspection coverage is improved, but maintenance complexity deteriorates

Engineering Contradiction:
Improveinspection coverageVSAvoidmaintenance complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal digitization system that can process inspection sheets for multiple different machines through a single platform. The system uses machine learning models trained to recognize various inspection sheet formats, enabling one system to handle diverse inspection documentation across multiple machines and reduces maintenance burden

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system merges multiple individual inspection sheets into a unified digital database, combining data from numerous machines into a single centralized system. This consolidation maintains comprehensive inspection coverage while simplifying maintenance by managing all inspection data through one integrated platform rather than separate systems for each machine

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3480728B1Method and system for extracting information from hand-marked industrial inspection sheets
Publication Date: 2023.03.29 TATA CONSULTANCY SERVICES LTD
  • EP3480728B1 patent drawingFigure 1
  • EP3480728B1 patent drawingFigure 2a
  • EP3480728B1 patent drawingFigure 2b

AI summary

Usually in industries, manual inspection of machines is performed, and to note down comments, inspection sheets are used. Though this is easy and convenient, when the data is to be inspected or checked at a later stage, multiple inspection sheets may have to be referred, and this turns out to be a cumbersome and time consuming process. Digitization of the inspection sheet can solve this issue. However, as the inspection sheets contain unstructured data, document digitization becomes a difficult process. System and method for digitization of inspection sheet are disclosed. In an embodiment, the system performs localization of text as well as arrows in the inspection sheet, and identifies text that matches each arrow. Further by identifying machine zone each arrow is pointing to, the system assigns corresponding text to the appropriate machine zone; thus facilitating digitization of the inspection sheets.